© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17674
    Prev
    Next
    INDEX
    Explanations

    asking questions or stating facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     是
    0.45
     does
    0.42
     "";
    0.42
     者
    0.41
     barg
    0.39
     kios
    0.39
     curricular
    0.39
     is
    0.38
     tests
    0.38
     子
    0.38
    POSITIVE LOGITS
    enin
    0.46
    nö
    0.44
     Ceram
    0.42
    ᱙
    0.41
    midt
    0.40
    CloseOperation
    0.40
    なって
    0.40
    ustain
    0.39
    anjut
    0.39
    zość
    0.39
    Activations Density 0.002%

    No Known Activations